Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    passive voice constructions with the verb "to be" followed by a past participle

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "has been" indicating ongoing situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odder
    -0.73
    rones
    -0.71
    ives
    -0.70
    terday
    -0.67
     Bars
    -0.67
     Relief
    -0.64
    arms
    -0.63
     Tycoon
    -0.62
     Wid
    -0.62
    lies
    -0.61
    POSITIVE LOGITS
     subjected
    0.99
     deemed
    0.98
     replaced
    0.96
     taken
    0.94
     shown
    0.94
     able
    0.94
     seen
    0.91
     likened
    0.90
     treated
    0.89
     unable
    0.88
    Act Density 0.167%

    No Known Activations